Search Results for author:
Found 2 papers, 0 papers with code
Mixability in Statistical Learning
We show that, in the special case of log-loss, stochastic mixability reduces to a well-known (but usually unnamed) martingale condition, which is used in existing convergence theorems for minimum description length and Bayesian inference.
Adaptive Hedge
In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case performance, leading to suboptimal performance on easy instances, for example when there exists an action that is significantly better than all others.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
